Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation

• URL: http://arxiv.org/abs/2608.09420v1
• Date: Mon, 10 Aug 2026 10:48:40 GMT
• Title: Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation
• Abstract summary: controllable user simulation should separate which local interaction intent the next user turn should realize from how that intent is expressed in language.<n>We introduce UserIDA, which exposes interaction intent as an explicit per-turn directive.<n>On LMSYS-USP, UserIDA achieves 86.6% intent accuracy, outperforming the strongest dedicated user-simulator baseline by 24.3 percentage points.
• Score: 25.422690765682788
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: User simulators are widely used as scalable environments for training and evaluating interactive assistants. Generating the next user turn is inherently one-to-many: the same profile and dialogue context may support multiple plausible continuations with different local interaction intents. A fluent response may therefore advance the dialogue through an inappropriate intent, such as acceptance rather than repair. Our key insight is that controllable user simulation should separate which local interaction intent the next user turn should realize from how that intent is expressed in language. We introduce UserIDA (User Intent-Directive Alignment), which exposes interaction intent as an explicit per-turn directive. UserIDA defines a six-way intent interface, learns directive-conditioned generation through supervised fine-tuning, and uses intent-calibrated policy optimization during group-based reinforcement learning. The reward preserves composite response quality while ensuring that intent-violating candidates rank below compliant alternatives in mixed groups. On LMSYS-USP, UserIDA achieves 86.6\% intent accuracy, outperforming the strongest dedicated user-simulator baseline by 24.3 percentage points while improving semantic and stylistic similarity. In within-context interventions, it realizes at least four of the six target intents in 91.7\% of evaluated dialogue states, compared with 22.9\% for the strongest external baseline. These results establish per-turn intent control as a complementary dimension to response fidelity in user simulation.

Related papers

• Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Context [12.546026856710148]
  Next-turn user reactions provide actionable local credit for improving multi-turn user-interacting agents.<n>textscFACA improves the nine-domain $$-family average across three independently trained runs.
  arXiv  Detail & Related papers  (2026-08-18T08:25:21Z)
• Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering [6.156855333798949]
  Intent-Aware Personalization (IAP) trains models to infer implicit user intent directly from a single-turn question.<n>IAP incorporates user intent into thinking steps through a tag-based schema for generating personalized, intent-grounded answers.<n>IAP consistently outperforms all baselines in experiments on the LaMP-QA benchmark.
  arXiv  Detail & Related papers  (2026-05-12T18:38:05Z)
• KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation [72.01173512175531]
  KnowU-Bench is an online benchmark for personalized mobile agents.<n>It covers 42 general GUI tasks, 86 personalized tasks, and 64 proactive tasks.<n>Our experiments reveal a striking degradation: agents that excel at explicit task execution fall below 50% under vague instructions.
  arXiv  Detail & Related papers  (2026-04-09T16:50:50Z)
• PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments [72.02445514666428]
  We introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall.<n>PerMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time.<n> Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption.
  arXiv  Detail & Related papers  (2026-03-24T14:04:11Z)
• IntPro: A Proxy Agent for Context-Aware Intent Understanding via Retrieval-conditioned Inference [22.214499732123173]
  IntPro is a proxy agent that learns to adapt to individual users via retrieval-conditioned intent inference.<n>We show that IntPro achieves strong intent understanding performance with effective context-aware reasoning capabilities.
  arXiv  Detail & Related papers  (2026-02-10T07:20:58Z)
• Search-Based Interaction For Conversation Recommendation via Generative Reward Model Based Simulated User [117.82681846559909]
  Conversational recommendation systems (CRSs) use multi-turn interaction to capture user preferences and provide personalized recommendations.<n>We propose a generative reward model based simulated user, named GRSU, for automatic interaction with CRSs.
  arXiv  Detail & Related papers  (2025-04-29T06:37:30Z)
• Mind the Gap! Static and Interactive Evaluations of Large Audio Models [55.87220295533817]
  Large Audio Models (LAMs) are designed to power voice-native experiences.<n>This study introduces an interactive approach to evaluate LAMs and collect 7,500 LAM interactions from 484 participants.
  arXiv  Detail & Related papers  (2025-02-21T20:29:02Z)
• Stop Playing the Guessing Game! Target-free User Simulation for Evaluating Conversational Recommender Systems [21.275452863162936]
  PEPPER is an evaluation protocol with target-free user simulators constructed from real-user interaction histories and reviews.<n> PEPPER enables realistic user-CRS dialogues without falling into simplistic guessing games.<n> PEPPER presents detailed measures for comprehensively evaluating the preference elicitation capabilities of CRSs.
  arXiv  Detail & Related papers  (2024-11-25T07:36:20Z)
• Adversarial learning of neural user simulators for dialogue policy optimisation [14.257597015289512]
  Reinforcement learning based dialogue policies are typically trained in interaction with a user simulator. Current data-driven simulators are trained to accurately model the user behaviour in a dialogue corpus. We propose an alternative method using adversarial learning, with the aim to simulate realistic user behaviour with more variation.
  arXiv  Detail & Related papers  (2023-06-01T16:17:16Z)
• Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbots [62.295373408415365]
  We propose a personalized hybrid matching network (PHMN) for context-response matching. Our contributions are two-fold: 1) our model extracts personalized wording behaviors from user-specific dialogue history as extra matching information. We evaluate our model on two large datasets with user identification, i.e., personalized dialogue Corpus Ubuntu (P- Ubuntu) and personalized Weibo dataset (P-Weibo)
  arXiv  Detail & Related papers  (2021-03-17T09:42:11Z)
• Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition [64.06167416127386]
  We propose Multi-Agent Dialog Policy Learning, which regards both the system and the user as the dialog agents. Two agents interact with each other and are jointly learned simultaneously. Results show that our method can successfully build a system policy and a user policy simultaneously.
  arXiv  Detail & Related papers  (2020-04-08T04:51:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.